{"meta":{"title":"Use voice input with Copilot CLI","intro":"Speak your prompts to GitHub Copilot CLI instead of typing them, using the CLI's speech-to-text feature.","product":"GitHub Copilot","breadcrumbs":[{"href":"/en/enterprise-cloud@latest/copilot","title":"GitHub Copilot"},{"href":"/en/enterprise-cloud@latest/copilot/how-tos","title":"How-tos"},{"href":"/en/enterprise-cloud@latest/copilot/how-tos/copilot-cli","title":"Copilot CLI"},{"href":"/en/enterprise-cloud@latest/copilot/how-tos/copilot-cli/use-copilot-cli","title":"Use Copilot CLI"},{"href":"/en/enterprise-cloud@latest/copilot/how-tos/copilot-cli/use-copilot-cli/voice-input","title":"Voice input"}],"documentType":"article"},"body":"# Use voice input with Copilot CLI\n\nSpeak your prompts to GitHub Copilot CLI instead of typing them, using the CLI's speech-to-text feature.\n\nVoice input lets you dictate prompts to Copilot CLI by speaking into your microphone instead of typing on the keyboard. Transcription runs entirely on your local machine. Your audio is not sent over the network. The recognized text is inserted at the cursor position in the prompt input area, where you can edit it before submitting.\n\n## Prerequisite\n\nYou need a working microphone connected to your machine. By default, voice input uses your system's default microphone.\n\n## Limitation\n\nVoice input is currently only supported for English and Spanish dictation. English is the default language for speech recognition.\n\n## Enabling voice input\n\nBefore you can dictate prompts, you need to download the voice runtime that powers speech recognition, and a voice model.\n\n1. In an interactive Copilot CLI session, enter the `/voice` slash command.\n\n2. When prompted, select **Continue** to download the voice runtime.\n\n   The download runs in the background. You can keep using Copilot CLI while it completes.\n\n3. When you're prompted to choose a voice model, press <kbd>Enter</kbd> with \"Download default model\" selected to download the English speech-to-text model.\n\n   Alternatively, if you want to dictate in Spanish:\n\n   1. Use the arrow keys on your keyboard to select \"Browse models\", then press <kbd>Enter</kbd>.\n   2. In the voice models picker, use the arrow keys to select the Spanish speech-to-text model, then press <kbd>Enter</kbd> to download it.\n   3. Press <kbd>Esc</kbd> to exit the picker.\n\n## Using voice input\n\nThere are two ways to dictate prompts.\n\n### For short prompts\n\n1. Hold down the space bar on your keyboard.\n\n   After a brief moment, recording begins.\n\n2. Speak your prompt.\n\n3. Release the space bar.\n\n   Copilot CLI transcribes your speech and inserts the result at the cursor position in the prompt input area.\n\n### For longer prompts\n\nRather than holding down the space bar, you can toggle voice recording on and off. This is more convenient for longer prompts.\n\n1. Press <kbd>Ctrl</kbd>+<kbd>X</kbd> followed by <kbd>V</kbd> to start recording.\n\n   > \\[!NOTE]\n   > In some terminals, you can use <kbd>Ctrl</kbd>+<kbd>Space</kbd> as an alternative. This shortcut only works if your terminal and OS pass it through. You may also need to free it in your terminal or OS key bindings.\n\n2. Speak your prompt.\n\n3. Press any key to stop recording and insert the transcription.\n\n### Cleaning up voice-entered prompts\n\nOptionally, to clean up a prompt you have entered by speaking, you can use the `/refine` slash command. This command:\n\n* Removes filler words, false starts or repetitions.\n* Applies any self-corrections you've made.\n* Fixes grammatical mistakes.\n* Groups related points for clarity.\n\nTo clean up the current prompt:\n\n1. Before submitting the prompt, press <kbd>Ctrl</kbd>+<kbd>X</kbd> quickly followed by <kbd>/</kbd>.\n2. Type `/refine`, then press <kbd>Enter</kbd>.\n\n## Switching microphones\n\nIf you have more than one microphone available on your system, you can switch input devices.\n\n1. Enter the `/voice devices` slash command.\n\n   A list of available input devices is shown.\n\n2. Use the arrow keys on your keyboard to select the microphone you want to use, then press <kbd>Enter</kbd>.\n\n## Switching voice models\n\nYou can dictate prompts in English or Spanish, but the appropriate voice model must be downloaded and activated for the language you want to use.\n\nTo change to a different voice model:\n\n1. Enter the `/voice models` slash command.\n\n   The voice models picker is displayed. A check mark indicates the currently active model.\n\n2. In the voice models picker, use the arrow keys on your keyboard to select the English or Spanish speech-to-text, then press <kbd>Enter</kbd>.\n\n   If the model is not already downloaded, it will be downloaded to your machine.\n\n3. If you downloaded a model, press <kbd>Enter</kbd> again to make it the active model.\n\nYour choice of model—and whether voice input is enabled or disabled—is stored in your Copilot settings file (typically `~/.copilot/settings.json`) so that your preferences persist across CLI sessions.\n\n## Further reading\n\n* [Using GitHub Copilot CLI](/en/enterprise-cloud@latest/copilot/how-tos/copilot-cli/use-copilot-cli/overview)"}